{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:IPY3CXN5ZP3TS2OHXNJTH463SV","short_pith_number":"pith:IPY3CXN5","schema_version":"1.0","canonical_sha256":"43f1b15dbdcbf73969c7bb5333f3db957317df0926ad7e930fc83c96fabf8f88","source":{"kind":"arxiv","id":"2309.09979","version":2},"attestation_state":"computed","paper":{"title":"General In-Hand Object Rotation with Vision and Touch","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.LG"],"primary_cat":"cs.RO","authors_text":"Brent Yi, Haozhi Qi, Jitendra Malik, Mike Lambeta, Roberto Calandra, Sudharshan Suresh, Yi Ma","submitted_at":"2023-09-18T17:59:25Z","abstract_excerpt":"We introduce RotateIt, a system that enables fingertip-based object rotation along multiple axes by leveraging multimodal sensory inputs. Our system is trained in simulation, where it has access to ground-truth object shapes and physical properties. Then we distill it to operate on realistic yet noisy simulated visuotactile and proprioceptive sensory inputs. These multimodal inputs are fused via a visuotactile transformer, enabling online inference of object shapes and physical properties during deployment. We show significant performance improvements over prior methods and the importance of v"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2309.09979","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2023-09-18T17:59:25Z","cross_cats_sorted":["cs.AI","cs.CV","cs.LG"],"title_canon_sha256":"e5a565bb8dc0b39eb75deebf7d1ceddd5e93a776f6deeb00cdb0f27d2182fe07","abstract_canon_sha256":"0044de9ade61d10504359e0f6a7fd1bfea25313e41324867f67639b8a750ad73"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:55:06.413213Z","signature_b64":"ZE0Es3h4Ce6vIY5xsjXz2xKoqcEWa68/8MSuny5Mh3OuncKr2JM3XfghuAaDTdZIx2zwwYK4bAud0ZSefGXACA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"43f1b15dbdcbf73969c7bb5333f3db957317df0926ad7e930fc83c96fabf8f88","last_reissued_at":"2026-07-05T06:55:06.412683Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:55:06.412683Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"General In-Hand Object Rotation with Vision and Touch","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.LG"],"primary_cat":"cs.RO","authors_text":"Brent Yi, Haozhi Qi, Jitendra Malik, Mike Lambeta, Roberto Calandra, Sudharshan Suresh, Yi Ma","submitted_at":"2023-09-18T17:59:25Z","abstract_excerpt":"We introduce RotateIt, a system that enables fingertip-based object rotation along multiple axes by leveraging multimodal sensory inputs. Our system is trained in simulation, where it has access to ground-truth object shapes and physical properties. Then we distill it to operate on realistic yet noisy simulated visuotactile and proprioceptive sensory inputs. These multimodal inputs are fused via a visuotactile transformer, enabling online inference of object shapes and physical properties during deployment. We show significant performance improvements over prior methods and the importance of v"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.09979","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2309.09979/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2309.09979","created_at":"2026-07-05T06:55:06.412748+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.09979v2","created_at":"2026-07-05T06:55:06.412748+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.09979","created_at":"2026-07-05T06:55:06.412748+00:00"},{"alias_kind":"pith_short_12","alias_value":"IPY3CXN5ZP3T","created_at":"2026-07-05T06:55:06.412748+00:00"},{"alias_kind":"pith_short_16","alias_value":"IPY3CXN5ZP3TS2OH","created_at":"2026-07-05T06:55:06.412748+00:00"},{"alias_kind":"pith_short_8","alias_value":"IPY3CXN5","created_at":"2026-07-05T06:55:06.412748+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.31236","citing_title":"TactX: Learning Shared Tactile Representations Across Diverse Sensors","ref_index":22,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IPY3CXN5ZP3TS2OHXNJTH463SV","json":"https://pith.science/pith/IPY3CXN5ZP3TS2OHXNJTH463SV.json","graph_json":"https://pith.science/api/pith-number/IPY3CXN5ZP3TS2OHXNJTH463SV/graph.json","events_json":"https://pith.science/api/pith-number/IPY3CXN5ZP3TS2OHXNJTH463SV/events.json","paper":"https://pith.science/paper/IPY3CXN5"},"agent_actions":{"view_html":"https://pith.science/pith/IPY3CXN5ZP3TS2OHXNJTH463SV","download_json":"https://pith.science/pith/IPY3CXN5ZP3TS2OHXNJTH463SV.json","view_paper":"https://pith.science/paper/IPY3CXN5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.09979&json=true","fetch_graph":"https://pith.science/api/pith-number/IPY3CXN5ZP3TS2OHXNJTH463SV/graph.json","fetch_events":"https://pith.science/api/pith-number/IPY3CXN5ZP3TS2OHXNJTH463SV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IPY3CXN5ZP3TS2OHXNJTH463SV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IPY3CXN5ZP3TS2OHXNJTH463SV/action/storage_attestation","attest_author":"https://pith.science/pith/IPY3CXN5ZP3TS2OHXNJTH463SV/action/author_attestation","sign_citation":"https://pith.science/pith/IPY3CXN5ZP3TS2OHXNJTH463SV/action/citation_signature","submit_replication":"https://pith.science/pith/IPY3CXN5ZP3TS2OHXNJTH463SV/action/replication_record"}},"created_at":"2026-07-05T06:55:06.412748+00:00","updated_at":"2026-07-05T06:55:06.412748+00:00"}